Technology for open-ended language generation, a key application of artificial intelligence, has advanced to a great extent in recent years. Large-scale language models, which are trained on large corpora of text, are being used in a wide range of applications everywhere, from virtual assistants to conversational bots. While these language models output fluent text, existing research shows that these models can and do capture human biases. Many of these biases, especially those that could potentially cause harm, are being well investigated. On the other hand, studies that infer and change personality traits inherited by these models have been scarce or non-existent. In this work, we explore the personality traits of several large-scale language models designed for open-ended text generation and the datasets used for training them. Our work builds on the popular Big Five factors and develops robust methods that quantify the personality traits of these models and their underlying datasets. In particular, we trigger the models with a questionnaire designed for personality assessment and subsequently classify the text responses into quantifiable traits using a Zero-shot classifier. Our classification sheds light on an important anthropomorphic element found in such AI models and can help stakeholders decide how they should be applied and how society could perceive them. We augment our analysis by studying approaches that can alter these personalities.
翻译:开放语言生成技术是人造智能的关键应用,近年来,这种技术已大有进展。大规模语言模型在各地广泛应用,从虚拟助理到对谈机器人,从虚拟助理到对口机器人。这些语言模型输出流畅的文字,但现有研究表明,这些模型能够并确实能够捕捉人类偏见。许多这些偏见,特别是可能造成损害的偏见,正在得到很好地调查。另一方面,这些模型遗留下来的个性特征的推论和改变研究很少或根本不存在。在这项工作中,我们探索了为开放式文本生成设计的若干大型语言模型的个性特征以及用于培训这些模型的数据集。我们的工作以流行的五大要素为基础,并开发了能够量化这些模型的个性特征及其基本数据集的有力方法。特别是,我们正在启动为个性评估设计的问卷模型,然后用Zero-shot分类器将文本答复分为可量化的特性。我们分类的分类工作揭示了为开放文本生成的几种大规模语言模型的特征的特征。我们的工作将一些大型语言模型的个性特征和用于培训它们所使用的数据集的个性特征。我们的工作建立在流行的五大要素之上,我们的工作可以利用这些要素,我们的工作可以研究这些模型,我们通过这些模型可以如何研究来研究这些特性如何改变这些特性,我们如何研究这些模型,我们如何研究这些特性如何研究这些模型,从而研究这些模型可以研究这些特性如何研究这些特性如何改变这些特性。